© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 12242
    Prev
    Next
    INDEX
    Explanations

    2 pulgadas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tela
    1.49
    Msg
    1.47
    𝙨
    1.45
    ar
    1.44
    َى
    1.41
    𝙧
    1.40
    तुम
    1.40
    বারে
    1.38
     Gustavo
    1.37
    חות
    1.35
    POSITIVE LOGITS
    ところが
    1.74
    Ѕ
    1.64
    ᅠ
    1.64
     такое
    1.61
    bicyclo
    1.59
    gments
    1.58
     Stellung
    1.57
     colitis
    1.53
     Bxa
    1.52
    ланган
    1.50
    Activations Density 0.046%

    No Known Activations